Processing Results from DADA2 to make plots, do some statistics

Link to notebook

Link to github repo.

Table of Contents

• Load packages
• Import and prepare the data from eDNA
  • Import metadata
  • Import DADA2 results
• QC and filtering eDNA dataset
  • Rarefaction curves
  • Filtering
  • Check sequencing effort
• Abundance plots eDNA
  • Abundance at family level
  • Bubble plots
• Import and prepare the data from trawls
  • Import Trawl Master sheet
  • Convert to count table
• Abundance plots Trawls
• Abundance Plots Compare Trawl and eDNA
• Exploratory Analyses
  • Ordinations on eDNA
    • PCA
    • PCoA Jaccard
    • PCoA Bray Curtis
    • NMDS Aitchison
    • NMDS Jacaard
    • NMDS Bray Curtis
    • eDNA Ordinations Summary

Load packages

library(tidyverse)
library(readxl)
library(phyloseq)
library(Biostrings)
#library(phangorn)
library(readr)
library(seqinr)
library(decontam)
library(ape)
library(vegan)
#library(philr)
library(RColorBrewer)
library(microbiome)
#library(DESeq2)
library(compositions);
library(cowplot)
library(plotly)
library(htmlwidgets)
library(withr)
library(lubridate)

Import and prepare the data from eDNA

Import metadata

metadata <- read_csv("sample_data.csv")

── Column specification ─────────────────────────────────────────────────────────────────
cols(
  SampleID = col_character(),
  `Year.Trawl#` = col_character(),
  Datecode = col_double(),
  Date = col_character(),
  Month = col_double(),
  Year = col_double(),
  Bayside = col_character(),
  Station = col_character(),
  Habitat = col_character(),
  DO = col_double(),
  Salinity = col_double(),
  Temperature = col_double()
)

Import DADA2 results

Import count table and taxonomy file. I slightly modified otutable.csv in Excel to otutable_mod.csv to remove the quotes around seq names and put NA placehoder as first col name (which was above row names)

# Import Count table. Skip first row of tsv file, which is just some text
count_table <- read_table2("results/otutable_mod.csv")

Missing column names filled in: 'X1' [1]
── Column specification ─────────────────────────────────────────────────────────────────
cols(
  .default = col_double(),
  X1 = col_character()
)
ℹ Use `spec()` for the full column specifications.

colnames(count_table)[1] <- "SampleID"

# Import taxonomy of ASVs
taxonomy <- read_csv(file="results/tax_sequences_blast_taxonomy.csv")

Missing column names filled in: 'X1' [1]Duplicated column names deduplicated: 'RefSeq_Tax_ID' => 'RefSeq_Tax_ID_1' [18]
── Column specification ─────────────────────────────────────────────────────────────────
cols(
  X1 = col_double(),
  ASV_ID = col_character(),
  ref_seq_ID = col_character(),
  PID = col_double(),
  alnmt_len = col_double(),
  mismatch = col_double(),
  eval = col_double(),
  bscore = col_double(),
  RefSeq_Tax_ID = col_double(),
  Ref_Seq_title = col_character(),
  superkingdom = col_character(),
  phylum = col_character(),
  class = col_character(),
  order = col_character(),
  family = col_character(),
  genus = col_character(),
  species = col_character(),
  RefSeq_Tax_ID_1 = col_double()
)

# remove first col of sequential numbers
taxonomy[,1] <- NULL
# filter out sequences with low PID (recommended by Sara)
taxonomy <- filter(taxonomy, PID > 92)

# remove BLAST metadata and just retain taxonomy (necessary for further processing below)
drop.cols <- c(colnames(taxonomy)[2:9],'RefSeq_Tax_ID_1')
taxonomy <-  select(taxonomy, -one_of(drop.cols))


# And import the Common names, as curated by Sara. Join to taxonomy
commonnames <- read_excel("Trawls MASTER 2020 _mod_ES.xlsx",7)
commonnames

taxonomy <- left_join(taxonomy, commonnames, by = "ASV_ID")
taxonomy

NA

Filtering removed seqs 110, 332 (Gobiosoma ginsburgi and Belone belone) Note for Sara should we consider setting this at 97% which is more robust and still leaves 334 unique ASVs (rather than 379 with the 92% cutoff in the settings above)

Preview datasets

count_table

taxonomy

metadata

Make phyloseq object

I want to use the phyloseq package for some plotting/ statistics, which first requires making phyloseq objects out of each of input data tables-

count_table_matrix <- as.matrix(count_table[,2:392]) # convert count table to matrix, leaving out character column of sample ID
rownames(count_table_matrix) <- count_table$SampleID # add back in Sample IDs as row names
ASV =   otu_table(count_table_matrix, taxa_are_rows =  FALSE)

taxonomy_matrix <- as.matrix(taxonomy[,2:9])
rownames(taxonomy_matrix) <- taxonomy$ASV_ID 
TAX =   tax_table(taxonomy_matrix)

META    =   sample_data(data.frame(metadata, row.names = metadata$`SampleID`))

First check that the inputs are in compatible formats by checking for ASV names with the phyloseq function, taxa_names

head(taxa_names(TAX))

[1] "Seq_1" "Seq_2" "Seq_3" "Seq_4" "Seq_5" "Seq_6"

head(taxa_names(ASV))

[1] "Seq_1" "Seq_2" "Seq_3" "Seq_4" "Seq_5" "Seq_6"

And check sample names were also detected

# Modify taxa names in ASV, which are formatted with the sample ID, underscor, fastq ID. Don't need this fastq ID anymore and want it to match the sample names from metadata
sample_names(ASV) <-  sample_names(ASV) %>%
  str_replace_all(pattern = "_S[:digit:]+",replacement = "")


head(sample_names(ASV))

[1] "T1PosCon" "T1S10"    "T1S11"    "T1S1"     "T1S2"     "T1S3"    

head(sample_names(META))

[1] "T1PosCon" "T1S1"     "T1S2"     "T1S3"     "T1S5"     "T1S6"    

And make the phyloseq object

ps <- phyloseq(ASV, TAX,    META)

QC and filtering eDNA dataset

Rarefaction curves

rarecurve(otu_table(ps), step=50, cex=0.5)

empty rows removed

# save as .eps
setEPS()
postscript("Figures/rarefaction.eps")

rarecurve(otu_table(ps), step=50, cex=0.5)

empty rows removed

dev.off()

quartz_off_screen 
                2 

Most samples look like they were sampled to completion. Be weary of T3S11, T1S2, and maybe T4S5

Filtering

Check some features of the phyloseq object

rank_names(ps)

[1] "superkingdom" "phylum"       "class"        "order"        "family"      
[6] "genus"        "species"      "CommonName"  

unique(tax_table(ps)[, "superkingdom"])

Taxonomy Table:     [2 taxa by 1 taxonomic ranks]:
        superkingdom
Seq_1   "Eukaryota" 
Seq_377 NA          

unique(tax_table(ps)[, "phylum"])

Taxonomy Table:     [3 taxa by 1 taxonomic ranks]:
        phylum      
Seq_1   "Chordata"  
Seq_368 "Arthropoda"
Seq_377 NA          

unique(tax_table(ps)[, "class"])

Taxonomy Table:     [5 taxa by 1 taxonomic ranks]:
        class           
Seq_1   "Actinopteri"   
Seq_63  "Mammalia"      
Seq_362 "Chondrichthyes"
Seq_368 "Insecta"       
Seq_377 NA              

There are some ASVs with NA as superkingdom, phylum, or class annotation- delete these.

ps <- subset_taxa(ps, !is.na(superkingdom) & !is.na(phylum) & !is.na(class))

unique(tax_table(ps)[, "superkingdom"])

Taxonomy Table:     [1 taxa by 1 taxonomic ranks]:
      superkingdom
Seq_1 "Eukaryota" 

unique(tax_table(ps)[, "phylum"])

Taxonomy Table:     [2 taxa by 1 taxonomic ranks]:
        phylum      
Seq_1   "Chordata"  
Seq_368 "Arthropoda"

unique(tax_table(ps)[, "class"])

Taxonomy Table:     [4 taxa by 1 taxonomic ranks]:
        class           
Seq_1   "Actinopteri"   
Seq_63  "Mammalia"      
Seq_362 "Chondrichthyes"
Seq_368 "Insecta"       

nrow(tax_table(ps)) # number of ASVs left

[1] 378

378 ASVs still remain…

Also check class Mammalia, to see if contamination or real:

tax_table(subset_taxa(ps, class == 'Mammalia'))

Taxonomy Table:     [8 taxa by 8 taxonomic ranks]:
        superkingdom phylum     class      order          family      genus  
Seq_63  "Eukaryota"  "Chordata" "Mammalia" "Primates"     "Hominidae" "Homo" 
Seq_88  "Eukaryota"  "Chordata" "Mammalia" "Artiodactyla" "Suidae"    "Sus"  
Seq_157 "Eukaryota"  "Chordata" "Mammalia" "Primates"     "Hominidae" "Homo" 
Seq_343 "Eukaryota"  "Chordata" "Mammalia" "Carnivora"    "Felidae"   "Felis"
Seq_369 "Eukaryota"  "Chordata" "Mammalia" "Artiodactyla" "Bovidae"   "Bos"  
Seq_378 "Eukaryota"  "Chordata" "Mammalia" "Primates"     "Hominidae" "Homo" 
Seq_383 "Eukaryota"  "Chordata" "Mammalia" "Primates"     "Hominidae" "Homo" 
Seq_389 "Eukaryota"  "Chordata" "Mammalia" "Primates"     "Hominidae" "Homo" 
        species        CommonName 
Seq_63  "Homo sapiens" "Human"    
Seq_88  "Sus scrofa"   "Wild boar"
Seq_157 "Homo sapiens" "Human"    
Seq_343 "Felis catus"  "Cat"      
Seq_369 "Bos taurus"   "Cattle"   
Seq_378 "Homo sapiens" "Human"    
Seq_383 "Homo sapiens" "Human"    
Seq_389 "Homo sapiens" "Human"    

These are human, wild boar, cat (…cat lady), and cattle. All are contamination so delete all Mammalia

ps <- subset_taxa(ps, !class == 'Mammalia')
unique(tax_table(ps)[, "class"])

Taxonomy Table:     [3 taxa by 1 taxonomic ranks]:
        class           
Seq_1   "Actinopteri"   
Seq_362 "Chondrichthyes"
Seq_368 "Insecta"       

Next check the “Insecta” entries

tax_table(subset_taxa(ps, class == 'Insecta'))

Taxonomy Table:     [2 taxa by 8 taxonomic ranks]:
        superkingdom phylum       class     order         family       genus        
Seq_368 "Eukaryota"  "Arthropoda" "Insecta" "Hymenoptera" "Formicidae" "Linepithema"
Seq_380 "Eukaryota"  "Arthropoda" "Insecta" "Hymenoptera" "Formicidae" "Linepithema"
        species              CommonName
Seq_368 "Linepithema humile" "Ant"     
Seq_380 "Linepithema humile" "Ant"     

The onlly Insecta is Linepithema humile, which are ants so delete these too..

ps <- subset_taxa(ps, !class == 'Insecta')
unique(tax_table(ps)[, "class"])

Taxonomy Table:     [2 taxa by 1 taxonomic ranks]:
        class           
Seq_1   "Actinopteri"   
Seq_362 "Chondrichthyes"

Check sequencing effort

Check overall how ASVs there are per sample

# First aglomerate the ASVs at the phylum level using the phyloseq function, tax_glom
superkingdomGlommed = tax_glom(ps, "superkingdom")

# and plot
plot_bar(superkingdomGlommed, x = "Sample")

ggsave(filename = "Figures/seqdepth.eps", plot = plot_bar(superkingdomGlommed, x = "Sample"), units = c("in"), width = 9, height = 6, dpi = 300, )# and save

Total sequences reveals certain samples had very low sequencing effort: T1S7, T1S8, T3S11, and, not as bad, T1S2 and T4S5

The rarefaction analysis also showed T1S2 and T4S5 samples were likely not sequenced to completion. Therefore remove these 5 samples from analysis

ps <- subset_samples(ps, !SampleID == "T1S7" & !SampleID == "T1S8" & !SampleID == "T3S11" & !SampleID == "T1S2" & !SampleID == "T4S5")

ps

phyloseq-class experiment-level object
otu_table()   OTU Table:         [ 368 taxa and 50 samples ]
sample_data() Sample Data:       [ 50 samples by 12 sample variables ]
tax_table()   Taxonomy Table:    [ 368 taxa by 8 taxonomic ranks ]

50 samples remaining with 368 ASVs

Remove Pos Controls (all hits in positive controls are the same family- I assume this is expected)

ps <- subset_samples(ps, !SampleID == "T1PosCon" & !SampleID == "T2PosCon" & !SampleID == "T3PosCon")
ps

phyloseq-class experiment-level object
otu_table()   OTU Table:         [ 368 taxa and 47 samples ]
sample_data() Sample Data:       [ 47 samples by 12 sample variables ]
tax_table()   Taxonomy Table:    [ 368 taxa by 8 taxonomic ranks ]

And lastly, correct some taxonomy: According to Sara, Engraulis encrasicolus (European anchovy) should be Anchoa mitchilli (Bay anchovy):

tax_table(ps) <- gsub(tax_table(ps), pattern = "Engraulis encrasicolus", replacement = "Anchoa mitchilli")  

47 samples remainwith 368 unique ASVs

Abundance plots eDNA

For plotting, use relative abundances (# of ASV sequences/sum total sequences in sample), calculated easily using microbiome::transform

ps_ra <- microbiome::transform(ps, transform = "compositional")

Export the relative abundance matrix so Sara can have it:

# Extract abundance matrix from the phyloseq object
RelAbun_matrix = as(otu_table(ps_ra), "matrix")

# Coerce to data.frame
RelAbun_dataframe = as.data.frame(RelAbun_matrix)

# Export
write.csv(RelAbun_dataframe,"results/otutable_relabun.csv", row.names = TRUE)

Abundance at family level

Then aglomerate the ASVs at the family level using the phyloseq function, tax_glom

familyGlommed_RA = tax_glom(ps_ra, "family")
family_barplot <- plot_bar(familyGlommed_RA, x = "Sample", fill = "family")
family_barplot

NOTES for Sara

• There are some samples, (T1S3, T1S6, T2S11, T3S10, T3S4, T3S5, T3S9, T4S4, T4S7, T5S7) which are composed almost exclusively of 1 family. This might be fine, but I’m not used to seeing this with prokaroytic data. Just want to check with you

Agglomerate by species to see if I get the same 38 unique species Sara sees:

speciesGlommed_RA = tax_glom(ps_ra, "CommonName")
speciesGlommed_RA

phyloseq-class experiment-level object
otu_table()   OTU Table:         [ 43 taxa and 47 samples ]
sample_data() Sample Data:       [ 47 samples by 12 sample variables ]
tax_table()   Taxonomy Table:    [ 43 taxa by 8 taxonomic ranks ]

tax_table(speciesGlommed_RA)

Taxonomy Table:     [43 taxa by 8 taxonomic ranks]:
        superkingdom phylum     class            order                family           
Seq_1   "Eukaryota"  "Chordata" "Actinopteri"    "Atheriniformes"     "Atherinopsidae" 
Seq_2   "Eukaryota"  "Chordata" "Actinopteri"    "Clupeiformes"       "Clupeidae"      
Seq_3   "Eukaryota"  "Chordata" "Actinopteri"    "Clupeiformes"       "Engraulidae"    
Seq_4   "Eukaryota"  "Chordata" "Actinopteri"    "Scombriformes"      "Pomatomidae"    
Seq_5   "Eukaryota"  "Chordata" "Actinopteri"    "Lutjaniformes"      "Lutjanidae"     
Seq_6   "Eukaryota"  "Chordata" "Actinopteri"    "Pleuronectiformes"  "Paralichthyidae"
Seq_7   "Eukaryota"  "Chordata" "Actinopteri"    "Clupeiformes"       "Clupeidae"      
Seq_9   "Eukaryota"  "Chordata" "Actinopteri"    "Gobiiformes"        "Gobiidae"       
Seq_10  "Eukaryota"  "Chordata" "Actinopteri"    "Pleuronectiformes"  "Scophthalmidae" 
Seq_11  "Eukaryota"  "Chordata" "Actinopteri"    "Perciformes"        "Serranidae"     
Seq_12  "Eukaryota"  "Chordata" "Actinopteri"    "Spariformes"        "Sparidae"       
Seq_15  "Eukaryota"  "Chordata" "Actinopteri"    NA                   "Sciaenidae"     
Seq_16  "Eukaryota"  "Chordata" "Actinopteri"    NA                   "Sciaenidae"     
Seq_17  "Eukaryota"  "Chordata" "Actinopteri"    "Labriformes"        "Labridae"       
Seq_19  "Eukaryota"  "Chordata" "Actinopteri"    "Perciformes"        "Cottidae"       
Seq_20  "Eukaryota"  "Chordata" "Actinopteri"    "Pleuronectiformes"  "Pleuronectidae" 
Seq_21  "Eukaryota"  "Chordata" "Actinopteri"    NA                   "Moronidae"      
Seq_22  "Eukaryota"  "Chordata" "Actinopteri"    "Syngnathiformes"    "Syngnathidae"   
Seq_30  "Eukaryota"  "Chordata" "Actinopteri"    "Pleuronectiformes"  "Paralichthyidae"
Seq_33  "Eukaryota"  "Chordata" "Actinopteri"    NA                   "Sciaenidae"     
Seq_34  "Eukaryota"  "Chordata" "Actinopteri"    "Labriformes"        "Labridae"       
Seq_36  "Eukaryota"  "Chordata" "Actinopteri"    "Anguilliformes"     "Anguillidae"    
Seq_38  "Eukaryota"  "Chordata" "Actinopteri"    "Scombriformes"      "Scombridae"     
Seq_40  "Eukaryota"  "Chordata" "Actinopteri"    "Perciformes"        "Gasterosteidae" 
Seq_44  "Eukaryota"  "Chordata" "Actinopteri"    "Cyprinodontiformes" "Fundulidae"     
Seq_50  "Eukaryota"  "Chordata" "Actinopteri"    "Atheriniformes"     "Atherinopsidae" 
Seq_52  "Eukaryota"  "Chordata" "Actinopteri"    "Gadiformes"         "Phycidae"       
Seq_54  "Eukaryota"  "Chordata" "Actinopteri"    "Scombriformes"      "Scombridae"     
Seq_57  "Eukaryota"  "Chordata" "Actinopteri"    "Perciformes"        "Triglidae"      
Seq_67  "Eukaryota"  "Chordata" "Actinopteri"    "Scombriformes"      "Scombridae"     
Seq_82  "Eukaryota"  "Chordata" "Actinopteri"    NA                   "Sciaenidae"     
Seq_84  "Eukaryota"  "Chordata" "Actinopteri"    "Gadiformes"         "Gadidae"        
Seq_102 "Eukaryota"  "Chordata" "Actinopteri"    "Clupeiformes"       "Engraulidae"    
Seq_103 "Eukaryota"  "Chordata" "Actinopteri"    "Perciformes"        "Cottidae"       
Seq_115 "Eukaryota"  "Chordata" "Actinopteri"    "Cyprinodontiformes" "Fundulidae"     
Seq_119 "Eukaryota"  "Chordata" "Actinopteri"    "Gadiformes"         "Phycidae"       
Seq_139 "Eukaryota"  "Chordata" "Actinopteri"    "Batrachoidiformes"  "Batrachoididae" 
Seq_141 "Eukaryota"  "Chordata" "Actinopteri"    "Scombriformes"      "Scombridae"     
Seq_181 "Eukaryota"  "Chordata" "Actinopteri"    "Tetraodontiformes"  "Tetraodontidae" 
Seq_231 "Eukaryota"  "Chordata" "Actinopteri"    "Gadiformes"         "Merlucciidae"   
Seq_359 "Eukaryota"  "Chordata" "Actinopteri"    "Perciformes"        "Triglidae"      
Seq_362 "Eukaryota"  "Chordata" "Chondrichthyes" "Myliobatiformes"    "Myliobatidae"   
Seq_372 "Eukaryota"  "Chordata" "Chondrichthyes" "Carcharhiniformes"  "Triakidae"      
        genus                species                         CommonName                
Seq_1   "Menidia"            "Menidia menidia"               "Atlantic silverside"     
Seq_2   "Brevoortia"         "Brevoortia tyrannus"           "Atlantic menhaden"       
Seq_3   "Engraulis"          "Anchoa mitchilli"              "Bay anchovy"             
Seq_4   "Pomatomus"          "Pomatomus saltatrix"           "Bluefish"                
Seq_5   "Lutjanus"           "Lutjanus griseus"              "Grey snapper"            
Seq_6   "Paralichthys"       "Paralichthys dentatus"         "Summer flounder"         
Seq_7   "Alosa"              "Alosa mediocris"               "Hickory shad"            
Seq_9   "Gobiosoma"          "Gobiosoma ginsburgi"           "Seaboard goby"           
Seq_10  "Scophthalmus"       "Scophthalmus aquosus"          "Windowpane flounder"     
Seq_11  "Centropristis"      "Centropristis striata"         "Black seabass"           
Seq_12  "Stenotomus"         "Stenotomus chrysops"           "Scup"                    
Seq_15  "Leiostomus"         "Leiostomus xanthurus"          "Spot"                    
Seq_16  "Menticirrhus"       "Menticirrhus saxatilis"        "Northern kingfish"       
Seq_17  "Tautoga"            "Tautoga onitis"                "Tautog"                  
Seq_19  "Myoxocephalus"      "Myoxocephalus aenaeus"         "Grubby sculpin"          
Seq_20  "Pseudopleuronectes" "Pseudopleuronectes americanus" "Winter flounder"         
Seq_21  "Morone"             "Morone saxatilis"              "Striped bass"            
Seq_22  "Syngnathus"         "Syngnathus fuscus"             "Northern pipefish"       
Seq_30  "Etropus"            "Etropus microstomus"           "Smallmouth flounder"     
Seq_33  "Cynoscion"          "Cynoscion regalis"             "Weakfish"                
Seq_34  "Tautogolabrus"      "Tautogolabrus adspersus"       "Cunner"                  
Seq_36  "Anguilla"           "Anguilla rostrata"             "American eel"            
Seq_38  "Thunnus"            "Thunnus obesus"                "Bigeye tuna"             
Seq_40  "Apeltes"            "Apeltes quadracus"             "Stickleback"             
Seq_44  "Fundulus"           "Fundulus majalis"              "Striped killifish"       
Seq_50  "Membras"            "Membras martinica"             "Rough silverside"        
Seq_52  "Urophycis"          "Urophycis floridana"           "Spotted hake"            
Seq_54  "Scomber"            "Scomber japonicus"             "Chub mackerel"           
Seq_57  "Prionotus"          "Prionotus carolinus"           "Northern searobin"       
Seq_67  "Thunnus"            "Thunnus thynnus"               "Atlantic bluefin tuna"   
Seq_82  "Bairdiella"         "Bairdiella chrysoura"          "American silver perch"   
Seq_84  "Microgadus"         "Microgadus tomcod"             "Atlantic tomcod"         
Seq_102 "Engraulis"          "Engraulis mordax"              "Bay anchovy"             
Seq_103 "Myoxocephalus"      "Myoxocephalus quadricornis"    "Fourhorn sculpin"        
Seq_115 "Fundulus"           "Fundulus heteroclitus"         "Mummichog"               
Seq_119 "Urophycis"          "Urophycis floridana"           "Red hake"                
Seq_139 "Opsanus"            "Opsanus tau"                   "Oyster toadfish"         
Seq_141 "Katsuwonus"         "Katsuwonus pelamis"            "Skipjack tuna"           
Seq_181 "Sphoeroides"        "Sphoeroides maculatus"         "Northern puffer"         
Seq_231 "Merluccius"         "Merluccius bilinearis"         "Silver hake"             
Seq_359 "Prionotus"          "Prionotus evolans"             "Striped searobin"        
Seq_362 "Rhinoptera"         "Rhinoptera bonasus"            "Cownose ray"             
Seq_372 "Mustelus"           "Mustelus canis"                "Dusky smooth-hound shark"

NOTES for Sara

• I am getting 43 unique species- which ones am I missing that should be removed?
• Also there are two species you are calling Bay anchovy- Engraulis mordax and Anchoa mitchilli. Should the Engraulis mordax be changed to Anchoa mitchilli, similar to Engraulis encrasicolus ?

Bubble plots

Based on my previous scripts with Cariaco Eukaryotic data

# convert ps object to dataframe using phyloseq's psmelt
species_df <- psmelt(speciesGlommed_RA)

# replace zeroes in the table with NA
species_df[species_df == 0] <- NA

# and remove rows with NAs in abundance  (this is so they don't appear as small dots in plot)
species_df <-  filter(species_df, !is.na(Abundance))

Plot by species, scientific name

speciesbubbleplot_eDNA_sciname <- ggplot(species_df, aes(x = Station, y = fct_rev(species), color = Station)) + # the fancy stuff around y (species) helps to present it in reverse order in the plot (from top to btm alphabetically)
  geom_point(aes(size = Abundance, fill = Station), color = "black", pch = 21)+
  scale_size(range = c(1,15)) +
  scale_size_area(breaks = c(0,.25,.5,.75,1), max_size = 6)+
  xlab("")+
  ylab("")+
  labs(size="Relative Abundance")+
  theme_bw() +
  scale_fill_brewer(palette="Paired") +
  theme(axis.title.x=element_blank(),
        axis.text.x=element_blank(),
        axis.ticks.x=element_blank()) +
  facet_grid(Datecode~Bayside, scales = "free", space = "free", drop= TRUE)

Scale for 'size' is already present. Adding another scale for 'size', which will
replace the existing scale.

speciesbubbleplot_eDNA_sciname

Plot by species common name

speciesbubbleplot_eDNA_comname <- ggplot(species_df, aes(x = Station, y = fct_rev(CommonName), color = Station)) + # the fancy stuff around y (CommonName) helps to present it in reverse order in the plot (from top to btm alphabetically)
  geom_point(aes(size = Abundance, fill = Station), color = "black", pch = 21)+
  scale_size(range = c(1,15)) +
  scale_size_area(breaks = c(0,.25,.5,.75,1), max_size = 6)+
  xlab("")+
  ylab("")+
  labs(size="Relative Abundance")+
  theme_bw() +
  scale_fill_brewer(palette="Paired") +
  theme(axis.title.x=element_blank(),
        axis.text.x=element_blank(),
        axis.ticks.x=element_blank()) +
  facet_grid(Datecode~Bayside, scales = "free", space = "free", drop= TRUE)

Scale for 'size' is already present. Adding another scale for 'size', which will
replace the existing scale.

speciesbubbleplot_eDNA_comname

Exportfigures

ggsave(filename = "Figures/speciesbubbleplot_eDNA_sciname.eps", plot = speciesbubbleplot_eDNA_sciname, units = c("in"), width = 7, height = 12, dpi = 300)

ggsave(filename = "Figures/speciesbubbleplot_eDNA_comname.eps", plot = speciesbubbleplot_eDNA_comname, units = c("in"), width = 7, height = 12, dpi = 300)

NOTE on above. The common name plot has two entries in the Bay anchovy row because, as mentioned above, there are two different species name that are labelled as Bay Anchovy. Is it OK to group these as same species (Anchoa mitchilli)

Import and prepare the data from trawls

Import Trawl Master sheet

# import 4th sheet from  Excel file which contains morphometric data for each individual collected for every date
trawl_master <- read_excel("Trawls MASTER 2020 _mod_ES.xlsx",4)
trawl_master

# and import 6th sheet which is station info
stations <- read_excel("Trawls MASTER 2020 _mod_ES.xlsx",6)
stations

NA

Convert to count table

Make an equivalent to an OTU table, grouping by date and location and representing counts for every unique species

trawl_counts <- trawl_master %>%
  group_by(DATECODE, STATION_NO, CommonName) %>%
  tally(name = "count")

trawl_counts

and link station names instead of numbers to count table

trawl_counts <- left_join(trawl_counts, stations, by = "STATION_NO")
trawl_counts

Remove 09/16/20 since there is no equivalent eDNA from that date

trawl_counts <- trawl_counts %>%
  filter(DATECODE != "20200916")

trawl_counts

Abundance plots Trawls

speciesbubbleplot_trawl_comname <- ggplot(trawl_counts, aes(x = STATION_NA, y = fct_rev(CommonName), color = STATION_NA)) + 
  geom_point(aes(size = log10(count), fill = STATION_NA), color = "black", pch = 21)+
  scale_size(range = c(1,15)) +
  scale_size_area(breaks = c(.01,.1, .3, .5, 1, 3), max_size = 6)+
  xlab("")+
  ylab("")+
  labs(size="Log(counts)", fill = "Station")+
  theme_bw() +
  scale_fill_brewer(palette="Paired") +
  theme(axis.title.x=element_blank(),
        axis.text.x=element_blank(),
        axis.ticks.x=element_blank()) +
  facet_grid(DATECODE~BAYSIDE, scales = "free", space = "free", drop= TRUE)

Scale for 'size' is already present. Adding another scale for 'size', which will
replace the existing scale.

speciesbubbleplot_trawl_comname

Export figure

ggsave(filename = "Figures/speciesbubbleplot_trawl_comname.eps", plot = speciesbubbleplot_trawl_comname, units = c("in"), width = 6.75, height = 13, dpi = 300)

Abundance Plots Compare Trawl and eDNA

Count unique species across all stations, grouped by date, for each method (trawl, eDNA)

trawl_uniques <- trawl_counts %>%
  group_by(DATECODE, CommonName) %>%
  summarise(Trawl_Count = sum(count, na.rm=TRUE))

`summarise()` regrouping output by 'DATECODE' (override with `.groups` argument)

trawl_uniques

eDNA_uniques <- species_df%>%
  group_by(Datecode, CommonName) %>%
  summarise(eDNA_RelAbun = sum(Abundance, na.rm=TRUE))

`summarise()` regrouping output by 'Datecode' (override with `.groups` argument)

eDNA_uniques

# Combine into one dataframe
trawl_eDNA_abun_table <- full_join(trawl_uniques, eDNA_uniques, by=c("CommonName" = "CommonName", "DATECODE" = "Datecode"))

trawl_eDNA_abun_table

Count total number of species from each method for each date

eDNA_richness <- tally(eDNA_uniques, name = "eDNA")
trawl_richness <- tally(trawl_uniques, name = "trawl")

speciesrichness <- full_join(eDNA_richness, trawl_richness, c("Datecode" = "DATECODE"))
speciesrichness <- pivot_longer(speciesrichness, !Datecode, names_to = "Method", values_to = "Richness")

speciesrichness$Datecode <- ymd(speciesrichness$Datecode) # convert to date format (better for plotting)

speciesrichness

Plot side-by-side

species_richness_plot <- ggplot(speciesrichness, aes(x =Datecode, y = Richness)) +
  geom_line(aes(color = Method), size = 3) +
  theme_bw() +
  xlab("") +
  ylab("Species Richness")

species_richness_plot

# export plot
ggsave(filename = "Figures/species_richness_plot.eps", plot = species_richness_plot, units = c("in"), width = 4, height = 3, dpi = 300)

NOTE on above- come back and remove trawl samples for which the eDNA samples were removed so that this is a fair comparison. Also remove non-MiFISH species from trawl? Check with Sara

Sum total number of species across all dates/ stations for entire study

species_sums_abun_table <- trawl_eDNA_abun_table %>%
  group_by(CommonName) %>%
  summarise(Trawl = sum(Trawl_Count, na.rm=TRUE), eDNA = (sum(eDNA_RelAbun, na.rm=TRUE))) %>%
  pivot_longer(!CommonName, names_to = "Method", values_to = "Abundance")

`summarise()` ungrouping output (override with `.groups` argument)

  
# turn zeroes to NA so they don't plot 
species_sums_abun_table <- na_if(species_sums_abun_table,0)

species_sums_abun_table

For each species, plot side-by-side comparison of abundance (summed over whole study) using each method

# First create a custom color scale to make this pretty
myColors <- colorRampPalette(brewer.pal(11,"Spectral"))(55)
names(myColors) <- levels(unique(species_sums_abun_table$CommonName))
colScale <- scale_colour_manual(name = "CommonName",values = myColors)

species_abun_sum_plot <- ggplot(species_sums_abun_table, aes(x = Abundance, y = reorder(CommonName, Abundance, function(x){sum(x,na.rm = TRUE)}), color = CommonName)) +
  geom_point(size = 5) +
  facet_wrap(~fct_rev(Method), scales = "free") +
  theme_bw() +
  xlab("Abundance") +
  ylab("") + 
  colScale +
  theme(legend.position = "none")

species_abun_sum_plot

Export plot

ggsave(filename = "Figures/species_abun_sum_plot.eps", plot = species_abun_sum_plot, units = c("in"), width = 7, height = 8, dpi = 300)

Exploratory Analyses

Ordinations on eDNA

I will try PCoA, PCA (the Euclidean PCoA) and NMDS ordinations in combination with different tranformations and distance metrics in order to see which explain the most variance in the dataset.

• NOTE- see this discussion and this paper on why CCA should not be used with CLR-transformed compositional data to explore correlations.

PCA

PCA is essentially a type of PCoA using the Euclidean distance matrix as input. When combined with a log-ratio transformation of the count table, this is deemed appropriate for compositional datasets. It is also recommended as a first step in exploratory analyses of sequencinging datasets.

First do a CLR, centered log ratio transformation of the absolute abundance data (after filtering), as suggested by Gloor et al. 2017

# Estimate covariance matrix for CLR-transformed ASV table
clr_asv_table_ps <- data.frame(compositions::clr(otu_table(ps)))

Generate the PCA and visualize axes

# Generate a Principle Component Analysis (PCA) and evaluated based on the eigen decomposition from sample covariance matrix. 
lograt_pca <- prcomp(clr_asv_table_ps) 
# NOTE- this is equivalent to first making a Euclidean distance matrix using the CLR data table and then running a PCoA. A Euclidean distance matrix of a log-transformed data table = an Aitchison distance matrix. So this is equivalent to the compositional methods listed in Gloor et al.

# Visual representation with a screeplot
lograt_variances <- as.data.frame(lograt_pca$sdev^2/sum(lograt_pca$sdev^2)) %>% #Extract axes
  # Format to plot
  select(PercVar = 'lograt_pca$sdev^2/sum(lograt_pca$sdev^2)') %>% 
  rownames_to_column(var = "PCaxis") %>% 
  data.frame
head(lograt_variances)

# Plot screeplot
ggplot(lograt_variances, aes(x = as.numeric(PCaxis), y = PercVar)) + 
  geom_bar(stat = "identity", fill = "grey", color = "black") +
  theme_minimal() +
  theme(axis.title = element_text(color = "black", face = "bold", size = 10),
        axis.text.y = element_text(color = "black", face = "bold"),
        axis.text.x = element_blank()) +
  labs(x = "PC axis", y = "% Variance", title = "Log-Ratio PCA Screeplot, CLR Tranformation")

Total variance explained by first three axes= 15.7 + 10.5 + 10.0 = 36.2%. Since the second and third axes are similar, plot in 3D with 3 axes.

Visualize the PCA-

# Extract variances from the clr pca
pca_lograt_frame <- data.frame(lograt_pca$x) %>% 
  rownames_to_column(var = "SampleID")

# Merge metadata into the pcoa data table
pca_lograt_frame <- left_join(pca_lograt_frame, metadata, by = "SampleID")
head(pca_lograt_frame)

# Select eigenvalues from dataframe, round to 4 places and multiply by 100 for plotting. These will be the axes for the 3-D plot
eigenvalues<-round(lograt_variances[,2], digits = 4)*100

# Plotly - 3-D
pca_lograt <- plot_ly(pca_lograt_frame, type='scatter3d', mode='markers',
        x=~PC1,y=~PC2,z=~PC3,colors=~brewer.pal(11,'Paired'),
        color=~Station, symbols = c('circle','diamond'), symbol=~Bayside)%>%
  layout(font=list(size=12),
         title='CLR-Euclidean PCA',
         scene=list(xaxis=list(title=paste0('Co 2 ',eigenvalues[2],'%'),
                               showticklabels=FALSE,zerolinecolor='black'),
                    yaxis=list(title=paste0('Co 3 ',eigenvalues[3],'%'),
                               showticklabels=FALSE,zerolinecolor='black'),
                    zaxis=list(title=paste0('Co 1 ',eigenvalues[1],'%'),
                               showticklabels=FALSE,zerolinecolor='black')))
# pca_lograt

# save in "Embedded_figures" directory so that it can be hosted at Github and embedded in this notebook
withr::with_dir('Embedded_figures', htmlwidgets::saveWidget(as_widget(pca_lograt), file="pca_lograt.html", selfcontained = F))

 

Summary The CLR-Euclidean PCA reveals there is some separation according to East vs West. The PCA only explains ~36% of the variance so keep going with different ordinations to see if there is a better representation

PCoA Jaccard

The more traditional approach to ordinations is to do a PCoA on a distance matrix such as Bray-Curtis, Jaccard, or Unifrac. When combined with a transformation, they become more appropriate for NGS data. One such common transformation is the Hellinger transformation.

The different distance matrices also tell you a few different things about the dataset so I will run try different one to try to see if I can tease those out.

Before calculating any distance matrix, do a transformation of the filtered count table. Hellinger transformation is the square root of the relative abundance, so calculate it based on the ps_ra object:

ps_hellinger <- transform_sample_counts(ps_ra, function(x){sqrt(x)})

First, Jaccard, which builds the distance matrix based on presence/absence between samples. It does not take into account relative abundance of the taxa. Therefore this functions well for determining differences driven by rare taxa, which are weighed the same as abundant taxa.

jac_dmat<-vegdist(otu_table(ps_hellinger),method="jaccard") # Jaccard dist metric
pcoa_jac<-ape::pcoa(jac_dmat) # perform PCoA

# Extract variances from pcoa, from jaccard calculated dist. metric
jac_variances <- data.frame(pcoa_jac$values$Relative_eig) %>% 
  select(PercVar = 'pcoa_jac.values.Relative_eig') %>% 
  rownames_to_column(var = "PCaxis") %>% 
  data.frame
head(jac_variances)

# Make a screeplot
ggplot(jac_variances, aes(x = as.numeric(PCaxis), y = PercVar)) + 
  geom_bar(stat = "identity", fill = "grey", color = "black") +
  theme_minimal() +
  theme(axis.title = element_text(color = "black", face = "bold", size = 10),
        axis.text.y = element_text(color = "black", face = "bold"),
        axis.text.x = element_blank()) +
  labs(x = "PC axis", y = "% Variance", title = "Jaccard PCoA Screeplot")

The first two axes (19.0 + 9.6 = 28.6) are OK. But plot the first 3 axes since the 2nd and 3rd explain a similar amount of variance, (19.0 + 9.6 + 8.4 = 37% total variance explained)

Plot in 3D with Plotly

# Extract variances from the jaccard pcoa
pcoa_jac_df <- data.frame(pcoa_jac$vectors) %>% 
  rownames_to_column(var = "SampleID")

# Merge metadata into the pcoa data table
pcoa_jac_df <- left_join(pcoa_jac_df, metadata, by = "SampleID")
head(pcoa_jac_df)

# Select eigenvalues from dataframe, round to 4 places and multiply by 100 for plotting. These will be the axes for the 3-D plot
eigenvalues<-round(jac_variances[,2], digits = 4)*100

# Plotly - 3-D
pcoa_jaccard <- plot_ly(pcoa_jac_df, type='scatter3d', mode='markers',
        x=~Axis.2,y=~Axis.3,z=~Axis.1,colors=~brewer.pal(11,'Paired'),
        color=~Station, symbols = c('circle','diamond'), symbol=~Bayside)%>%
  layout(font=list(size=12),
         title='PCoA Jaccard Distance',
         scene=list(xaxis=list(title=paste0('Co 2 ',eigenvalues[2],'%'),
                               showticklabels=FALSE,zerolinecolor='black'),
                    yaxis=list(title=paste0('Co 3 ',eigenvalues[3],'%'),
                               showticklabels=FALSE,zerolinecolor='black'),
                    zaxis=list(title=paste0('Co 1 ',eigenvalues[1],'%'),
                               showticklabels=FALSE,zerolinecolor='black')))
# pcoa_jaccard

# save in "Embedded_figures" directory so that it can be hosted at Github and embedded in this notebook
withr::with_dir('Embedded_figures', htmlwidgets::saveWidget(as_widget(pcoa_jaccard), file="pcoa_jaccard.html", selfcontained = F))

The Jaccard-PCoA shows some separation along axis 2 and axis 3 in East vs West differences.

PCoA Bray Curtis

Next, try a Bray-Curtis distance matrix with PCoA, which builds the distance matrix based on presence/absence between samples and relative abundance differences. This ordination will represent well the differences in samples that are driven by taxa with high relative abundances.

NOTE: I need to use a correction here for negative eigenvalues. Read more here

bray_dmat<-vegdist(otu_table(ps_hellinger),method="bray") # Bray-Curtis dist metric
pcoa_bray<-ape::pcoa(bray_dmat) # perform PCoA in ape. But getting negative eigenvalues, so need to add correction. wcmdscale from base R also performs PCoA and can add cailliez correction
pcoa_bray <- wcmdscale(bray_dmat, eig = TRUE, add = "cailliez")

# check out summary of PCoA
eigenvals(pcoa_bray) %>%
  summary() -> ev
ev

Importance of components:
                        [,1]   [,2]    [,3]    [,4]    [,5]    [,6]    [,7]    [,8]
Eigenvalue            6.3464 3.2976 2.85913 1.62791 1.33454 1.24845 1.00909 0.90344
Proportion Explained  0.2111 0.1097 0.09511 0.05415 0.04439 0.04153 0.03357 0.03005
Cumulative Proportion 0.2111 0.3208 0.41591 0.47006 0.51445 0.55598 0.58955 0.61960
                         [,9]   [,10]   [,11]   [,12]   [,13]   [,14]  [,15]  [,16]
Eigenvalue            0.87308 0.77983 0.71209 0.65600 0.60628 0.54828 0.4990 0.4418
Proportion Explained  0.02904 0.02594 0.02369 0.02182 0.02017 0.01824 0.0166 0.0147
Cumulative Proportion 0.64864 0.67458 0.69827 0.72009 0.74026 0.75849 0.7751 0.7898
                        [,17]   [,18]  [,19]  [,20]   [,21]   [,22]   [,23]    [,24]
Eigenvalue            0.40560 0.39289 0.3668 0.3488 0.33712 0.33131 0.30233 0.285332
Proportion Explained  0.01349 0.01307 0.0122 0.0116 0.01121 0.01102 0.01006 0.009491
Cumulative Proportion 0.80328 0.81635 0.8285 0.8401 0.85136 0.86238 0.87244 0.881932
                         [,25]    [,26]   [,27]    [,28]    [,29]    [,30]    [,31]
Eigenvalue            0.268800 0.255859 0.24770 0.239363 0.226397 0.217778 0.198829
Proportion Explained  0.008941 0.008511 0.00824 0.007962 0.007531 0.007244 0.006614
Cumulative Proportion 0.890874 0.899385 0.90762 0.915586 0.923117 0.930361 0.936975
                         [,32]    [,33]    [,34]    [,35]   [,36]    [,37]    [,38]
Eigenvalue            0.194478 0.186212 0.167167 0.156242 0.15362 0.151123 0.139519
Proportion Explained  0.006469 0.006194 0.005561 0.005197 0.00511 0.005027 0.004641
Cumulative Proportion 0.943444 0.949639 0.955199 0.960397 0.96551 0.970534 0.975175
                         [,39]    [,40]    [,41]    [,42]    [,43]    [,44]    [,45]
Eigenvalue            0.133554 0.127736 0.124257 0.110435 0.106545 0.085716 0.058069
Proportion Explained  0.004443 0.004249 0.004133 0.003674 0.003544 0.002851 0.001932
Cumulative Proportion 0.979617 0.983866 0.987999 0.991673 0.995217 0.998068 1.000000

# extract variances and put in tibble
bray_variances <- NULL
for (i in 1:length(eigenvals(pcoa_bray))){
  bray_variances[i] <- eigenvals(pcoa_bray)[i]/sum(eigenvals(pcoa_bray))
}

# Extract variances from pcoa, from calculated dist. metric
bray_variances <- tibble(round(bray_variances,3)) %>%
  select(PercVar = 'round(bray_variances, 3)') %>%
  rownames_to_column(var = "PCaxis") %>%
  data.frame
head(bray_variances)

# Make a screeplot
ggplot(bray_variances, aes(x = as.numeric(PCaxis), y = PercVar)) + 
  geom_bar(stat = "identity", fill = "grey", color = "black") +
  theme_minimal() +
  theme(axis.title = element_text(color = "black", face = "bold", size = 10),
        axis.text.y = element_text(color = "black", face = "bold"),
        axis.text.x = element_blank()) +
  labs(x = "PC axis", y = "% Variance", title = "Bray-Curtis PCoA Screeplot")

The first two axes (21.1 + 11.0) are pretty good again but I am still going to experiment in the plot with the 3rd axis since it is similar to the second (9.5%; total variance explained = 41.6%)

Plot in 3D with Plotly

# Extract variances from the pcoa

There were 18 warnings (use warnings() to see them)

pcoa_bray_df <- data.frame(pcoa_bray$points) %>% 
  rownames_to_column(var = "SampleID")

# Merge metadata into the pcoa data table
pcoa_bray_df <- left_join(pcoa_bray_df, metadata, by = "SampleID")
head(pcoa_bray_df)

# Select eigenvalues from dataframe, round to 4 places and multiply by 100 for plotting. These will be the axes for the 3-D plot
eigenvalues<-round(bray_variances[,2], digits = 4)*100

# Plotly - 3-D
pcoa_bray <- plot_ly(pcoa_bray_df, type='scatter3d', mode='markers', 
                     x=~Dim2, y=~Dim3, z=~Dim1, colors=~brewer.pal(11,'Paired'),
        color=~Station, symbols = c('circle','diamond'), symbol=~Bayside)%>%  
  layout(font=list(size=12),
         title='PCoA Bray-Curtis Distance',
         scene=list(xaxis=list(title=paste0('Co 2 ',eigenvalues[2],'%'),
                               showticklabels=FALSE,zerolinecolor='black'),
                    yaxis=list(title=paste0('Co 3 ',eigenvalues[3],'%'),
                               showticklabels=FALSE,zerolinecolor='black'),
                    zaxis=list(title=paste0('Co 1 ',eigenvalues[1],'%'),
                               showticklabels=FALSE,zerolinecolor='black')))
# pcoa_bray

# save in "Embedded_figures" directory so that it can be hosted at Github and embedded in this notebook
withr::with_dir('Embedded_figures', htmlwidgets::saveWidget(as_widget(pcoa_bray), file="pcoa_bray.html", selfcontained = F))

`arrange_()` was deprecated in dplyr 0.7.0.
Please use `arrange()` instead.
See vignette('programming') for more help

These results along axes 1, 2, and 3 are similar to Jaccard, but there is MORE separation along axis 2, indicating that incorporating the differences in abundance helps explain more variance in the dataset.

NMDS Aitchison

Lastly, try a non-metric dimensional scaling ordination. PCA/PCoA are metric and attempt to rotate axes to fit the distance matrix distribution. An NMDS represents the data in 2-axes, by constraining the distribution of the points. Similar to above, this can be combined with different pre-treatment of the data.

First try the compositional approach, an NMDS on CLR-tranformed data using the Euclidean distances (aka Aitchison distance)

euc_dmat<-dist(clr_asv_table_ps, method = "euclidean") # Build the Aitchison distance matrix

There were 50 or more warnings (use warnings() to see the first 50)

euc_nmds <- metaMDS(euc_dmat, k=2, autotransform=FALSE) # Run the ordination

Run 0 stress 0.2105436 
Run 1 stress 0.210743 
... Procrustes: rmse 0.01868597  max resid 0.06267382 
Run 2 stress 0.2284121 
Run 3 stress 0.2281367 
Run 4 stress 0.2154902 
Run 5 stress 0.2169974 
Run 6 stress 0.2128146 
Run 7 stress 0.2123984 
Run 8 stress 0.2129377 
Run 9 stress 0.2321112 
Run 10 stress 0.2129288 
Run 11 stress 0.2324063 
Run 12 stress 0.2127399 
Run 13 stress 0.2110277 
... Procrustes: rmse 0.02376164  max resid 0.09749588 
Run 14 stress 0.2148974 
Run 15 stress 0.2109046 
... Procrustes: rmse 0.01881004  max resid 0.06376019 
Run 16 stress 0.2150601 
Run 17 stress 0.2314828 
Run 18 stress 0.2112384 
Run 19 stress 0.2128146 
Run 20 stress 0.2126376 
*** No convergence -- monoMDS stopping criteria:
     1: no. of iterations >= maxit
    19: stress ratio > sratmax

euc_nmds$stress #Check the stress. Less than 0.1 is good. Less than 0.05 is better. This will be different each time, since it is iteratively finding a unique solution each time (although the should look similar)

[1] 0.2105436

# Extract points from nmds and merge into data frame with metadata 
euc_nmds_df <- data.frame(euc_nmds$points) %>% 
  rownames_to_column(var = "SampleID")

# Merge metadata into the pcoa data table
euc_nmds_df <- left_join(euc_nmds_df, metadata, by = "SampleID")
head(euc_nmds_df)

## Plotting euclidean distance NMDS
nmds_aitch <- ggplot(euc_nmds_df,aes(x = MDS1, y = MDS2, color = Station, shape = Bayside)) +
  geom_point(size = 4) +
  scale_color_brewer(palette="Paired") +
  theme_bw() +
  labs(x = "NMDS 1", y = "NMDS 2", title = paste0('Aitchison Distance NMDS, Stress = ', round(euc_nmds$stress,2))) +
  coord_fixed(ratio = 1)

nmds_aitch

ggsave("figures/nmds_aitch.eps",nmds_aitch, width = 7, height = 5, units = c("in"))

The above has a relatively high stress (>0.2) so should be interpreted with caution. But it does show some separation East vs West along NMDS 1.

NMDS Jacaard

Next try a Jaccard NMDS, which will represent differences in presence/absence among samples, emphasizing both abundant and rare taxa the same

jac_nmds <- metaMDS(jac_dmat, k=2, autotransform=FALSE) # Run the ordination. Distance matrix was already calculated above

Run 0 stress 0.1627003 
Run 1 stress 0.1635518 
Run 2 stress 0.1913278 
Run 3 stress 0.187493 
Run 4 stress 0.1850804 
Run 5 stress 0.1574296 
... New best solution
... Procrustes: rmse 0.09013991  max resid 0.3060624 
Run 6 stress 0.1496846 
... New best solution
... Procrustes: rmse 0.0611786  max resid 0.3342008 
Run 7 stress 0.1758766 
Run 8 stress 0.1496646 
... New best solution
... Procrustes: rmse 0.05213047  max resid 0.3264531 
Run 9 stress 0.1512066 
Run 10 stress 0.1496492 
... New best solution
... Procrustes: rmse 0.002075288  max resid 0.01112514 
Run 11 stress 0.1511994 
Run 12 stress 0.1747511 
Run 13 stress 0.164175 
Run 14 stress 0.1635021 
Run 15 stress 0.1578622 
Run 16 stress 0.1741207 
Run 17 stress 0.1805795 
Run 18 stress 0.150871 
Run 19 stress 0.150871 
Run 20 stress 0.1809297 
*** No convergence -- monoMDS stopping criteria:
     1: no. of iterations >= maxit
    19: stress ratio > sratmax

jac_nmds$stress #Check the stress. Less than 0.1 is good. Less than 0.5 is better. This will be different each time, since it is iteratively finding a unique solution each time (although the should look similar)

[1] 0.1496492

# Extract points from nmds and merge into data frame with metadata 
jac_nmds_df <- data.frame(jac_nmds$points) %>% 
  rownames_to_column(var = "SampleID")

# Merge metadata into the pcoa data table
jac_nmds_df <- left_join(jac_nmds_df, metadata, by = "SampleID")
head(jac_nmds_df)

## Plotting euclidean distance NMDS
nmds_jaccard <- ggplot(jac_nmds_df,aes(x = MDS1, y = MDS2, color = Station, shape = Bayside)) +
  geom_point(size = 4) +
  scale_color_brewer(palette="Paired") +
  theme_bw() +
  labs(x = "NMDS 1", y = "NMDS 2", title = paste0('Jaccard Distance NMDS, Stress = ', round(jac_nmds$stress,2))) +
  coord_fixed(ratio = 1)

nmds_jaccard

ggsave("figures/nmds_jaccard.eps",nmds_jaccard, width = 7, height = 5, units = c("in"))

This is still a moderately high stress (>0.1) so should be interpreted with caution. Similar to Aitchison-distance nMDS but there is a little more separation of East vs West on NMDS 2 axis.

NMDS Bray Curtis

Next try a Bray-Curis NMDS, which will represent differences in presence/absence among samples and relative abundance, thus emphasizing impacts of highly abundant taxa.

bray_nmds <- metaMDS(bray_dmat, k=2, autotransform=FALSE) # Run the ordination. Distance matrix was already calculated above

Run 0 stress 0.1628608 
Run 1 stress 0.1496857 
... New best solution
... Procrustes: rmse 0.08605306  max resid 0.3199495 
Run 2 stress 0.1575236 
Run 3 stress 0.1648221 
Run 4 stress 0.1496852 
... New best solution
... Procrustes: rmse 0.001000773  max resid 0.005543388 
... Similar to previous best
Run 5 stress 0.1816327 
Run 6 stress 0.1574077 
Run 7 stress 0.16342 
Run 8 stress 0.1495163 
... New best solution
... Procrustes: rmse 0.05077312  max resid 0.3254243 
Run 9 stress 0.1496857 
... Procrustes: rmse 0.05076782  max resid 0.3264084 
Run 10 stress 0.1569837 
Run 11 stress 0.1700137 
Run 12 stress 0.149831 
... Procrustes: rmse 0.05229099  max resid 0.3259367 
Run 13 stress 0.1711916 
Run 14 stress 0.1634202 
Run 15 stress 0.164822 
Run 16 stress 0.1496496 
... Procrustes: rmse 0.01267154  max resid 0.07708813 
Run 17 stress 0.1667643 
Run 18 stress 0.1758516 
Run 19 stress 0.1660923 
Run 20 stress 0.1508713 
*** No convergence -- monoMDS stopping criteria:
     1: no. of iterations >= maxit
    19: stress ratio > sratmax

bray_nmds$stress #Check the stress. Less than 0.1 is good. Less than 0.5 is better. This will be different each time, since it is iteratively finding a unique solution each time (although the should look similar)

[1] 0.1495163

# Extract points from nmds and merge into data frame with metadata 
bray_nmds_df <- data.frame(bray_nmds$points) %>% 
  rownames_to_column(var = "SampleID")

# Merge metadata into the pcoa data table
bray_nmds_df <- left_join(bray_nmds_df, metadata, by = "SampleID")
head(bray_nmds_df)

## Plotting euclidean distance NMDS
nmds_bray <- ggplot(bray_nmds_df,aes(x = MDS1, y = MDS2, color = Station, shape = Bayside)) +
  geom_point(size = 4) +
  scale_color_brewer(palette="Paired") +
  theme_bw() +
  labs(x = "NMDS 1", y = "NMDS 2", title = paste0('Bray-Curtis Distance NMDS, Stress = ', round(bray_nmds$stress,2))) +
  coord_fixed(ratio = 1)

nmds_bray

ggsave("figures/nmds_bray.eps",nmds_bray, width = 7, height = 5, units = c("in"))

Very similar to Jaccard results. Moderately high stress (0.15)

eDNA Ordinations Summary

The ordination that explained the most variance in the eDNA dataset was the PCoA using the Bray-Curtis dissimilarity matrix after Hellinger transformation. This is similar to the approach presented in Lacoursière‐Roussel et al. 2018.

• Next: fit environmental vectors to this ordination to see which can be possibly explain some of the variation among samples and among species.

PCoA with Environmental Variables

Recreate, in 2D, the first two axes of the ordination (PCoA with Bray distance matrx/ Hellinger transformation) and use envfit from vegan to test and fit environmental variables.

If not making 3D plots, can do this directly in phyloseq (eg. https://www.gdc-docs.ethz.ch/MDA/handouts/MDA20_PhyloseqFormation_Mahendra_Mariadassou.pdf)

—— Fix below after plot above is fixed- Cant use phyloseqs pcoa ordination with cailliez correction

Check how samples differ in the ordination according to different environmental variables

Bayside

plot_ordination(ps_hellinger, ps_hellinger_bray_pcoa, color = "Bayside") +
  geom_point(size = 4) +
  stat_ellipse(aes(group = Bayside)) +
  ggtitle('Bray Curtis PCoA') +
  coord_fixed(ratio = 1) +
  theme_bw()

Summary: There is overlap of the two, but there are also many EAST samples that fall outside and do no look similar to WEST samples. The transition correlates with axis 2. The WEST samples are more closely clustered together than EAST samples.

Habitat

plot_ordination(ps_hellinger, ps_hellinger_bray_pcoa, color = "Habitat") +
  geom_point(size = 4) +
  stat_ellipse(aes(group = Habitat)) +
  ggtitle('Bray Curtis PCoA') +
  coord_fixed(ratio = 1) +
  theme_bw()

Summary there doesn’t seem to be any effect of habitat type

Date

plot_ordination(ps_hellinger, ps_hellinger_bray_pcoa, color = "Date") +
  geom_point(size = 4) +
  stat_ellipse(aes(group = Date)) +
  ggtitle('Bray Curtis PCoA') +
  coord_fixed(ratio = 1) +
  theme_bw()

Summary There seems to be a continuous transition from July 22 to Sept. 2 but isn’t parallel to either axis 1 or 2.

Vector fitting of numeric variables

# vegan doesn't do a pcoa. try cmdscale from base R on the bray curtis distance matrix (after hellinger transformation)
pcoa <- wcmdscale(bray_dmat, eig = TRUE)

eigenvals(pcoa) %>%
  summary() -> ev

ev

Importance of components:
                        [,1]   [,2]   [,3]    [,4]    [,5]    [,6]    [,7]    [,8]
Eigenvalue            4.2258 2.1784 1.8551 1.01077 0.78507 0.74604 0.57803 0.49798
Proportion Explained  0.2769 0.1428 0.1216 0.06624 0.05145 0.04889 0.03788 0.03263
Cumulative Proportion     NA     NA     NA      NA      NA      NA      NA      NA
                         [,9]  [,10]   [,11]   [,12]   [,13]   [,14]  [,15]  [,16]
Eigenvalue            0.48126 0.4089 0.35895 0.32230 0.29289 0.25365 0.2198 0.1816
Proportion Explained  0.03154 0.0268 0.02352 0.02112 0.01919 0.01662 0.0144 0.0119
Cumulative Proportion      NA     NA      NA      NA      NA      NA     NA     NA
                        [,17]   [,18]    [,19]    [,20]    [,21]    [,22]   [,23]
Eigenvalue            0.15789 0.15153 0.129958 0.120610 0.115693 0.101967 0.08697
Proportion Explained  0.01035 0.00993 0.008517 0.007904 0.007582 0.006682 0.00570
Cumulative Proportion      NA      NA       NA       NA       NA       NA      NA
                        [,24]    [,25]    [,26]    [,27]    [,28]    [,29]    [,30]
Eigenvalue            0.07843 0.069186 0.060555 0.054821 0.051491 0.036271 0.029569
Proportion Explained  0.00514 0.004534 0.003968 0.003593 0.003374 0.002377 0.001938
Cumulative Proportion      NA       NA       NA       NA       NA       NA       NA
                         [,31]    [,32]    [,33]    [,34]     [,35]     [,36]      [,37]
Eigenvalue            0.024343 0.023518 0.018367 0.013871 0.0077006 0.0052630 -2.106e-05
Proportion Explained  0.001595 0.001541 0.001204 0.000909 0.0005046 0.0003449  1.380e-06
Cumulative Proportion       NA       NA       NA       NA        NA        NA         NA
                           [,38]      [,39]     [,40]     [,41]     [,42]     [,43]
Eigenvalue            -0.0077983 -0.0101807 -0.017069 -0.027714 -0.037663 -0.046618
Proportion Explained   0.0005111  0.0006672  0.001119  0.001816  0.002468  0.003055
Cumulative Proportion         NA         NA        NA        NA        NA        NA
                          [,44]     [,45]    [,46]
Eigenvalue            -0.060747 -0.100417 -0.16686
Proportion Explained   0.003981  0.006581  0.01093
Cumulative Proportion        NA        NA       NA